Serve as the lead developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, MCP servers) that drive measurable return on investment.
Architect and code the "connective tissue" between Google’s AI products and customer's live infrastructure, including APIs, legacy data silos, and security perimeters.
Build high-performance evaluation (Eval) pipelines and observability frameworks to ensure agentic systems meet requirements for accuracy, safety, and latency.
Identify repeatable field patterns and technical "friction points" in Google’s AI stack, converting them into reusable modules or formal product feature requests for the Engineering teams.
Co-build with customer engineering teams to instill Google-grade development best practices, ensuring long-term project success and high end-user adoption.
Minimum qualifications:
Bachelor's degree in Computer Science or equivalent practical experience.
Experience coding in one or more general purpose languages (e.g., Python, Java, Go, C or C++) including data structures, algorithms, and software design.
Experience implementing multi-agent systems using frameworks (e.g., LangGraph, CrewAI, etc.) and patterns like ReAct, self-reflection, and hierarchical delegation.
Experience building machine learning solutions and working with technical customers.
Preferred qualifications:
Experience working with recommendation engines, data pipelines, or distributed machine learning.
Experience with deep learning frameworks (e.g. Tensorflow, pyTorch, XGBoost).
Knowledge of data warehousing concepts, including data warehouse technical architectures, infrastructure components, ETL/ ELT and reporting/analytic tools and environments (e.g. Apache Beam, Hadoop, Spark, Pig, Hive, MapReduce, Flume).
Knowledge of LLM-native metrics (tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing.
Understanding of the auxiliary practical concerns in production machine learning systems.
Ability to implement secure agentic workflows incorporating MCP, tool-calling, and OAuth-based authentication.
